We study outdoor 3D scene understanding, a challenging task demanding the intelligent system to infer both geometry and semantics from a single-view image – a critical skill for autonomous vehicles to navigate in the real 3D world. Towards this end, we present an instance-aware monocular semantic scene completion framework. To the best of our knowledge, this is the first endeavor specifically targeting the challenge of instance perception in the camera-based semantic scene completion task. Our method consists of two stages. In stage I, we design a region-based VQ-VAE network, providing an effective solution for 3D occupancy prediction. In stage II, we first introduce an instance-aware attention module, explicitly incorporating instance-level cues captured from mask images to enhance the instance features in RGB images. Then we leverage the deformable cross-attention to aggregate image features corresponding to each voxel query and utilize the deformable self-attention to refine query proposals. We combine these key ingredients and evaluate our method on two challenging datasets, namely SemanticKITTI and SSCBench-KITTI-360. The results unequivocally demonstrate the superiority of our proposed method over the state-of-the-art VoxFormer-S. Specifically, our method surpasses VoxFormer-S by 0.22 IoU and 0.72 mIoU on the validation set and achieves an impressive improvement of 3.04 IoU and 1.06 mIoU on the SSCBench-KITTI-360 validation set. Meanwhile, our approach ensures accurate perception of critical instances, thereby exhibiting its exceptional performance and potential for practical deployment.

Real-scanned point clouds are often incomplete due to occlusion, light reflection and limitations of sensor resolution, which impedes the related progress of downstream tasks, e.g., shape classification and object detection. Although there has been impressive research progress on the point cloud completion topic, they rely on the premise of extensive paired training data. However, collecting complete point clouds in some specified scenarios is labor-intensive and even impractical. To mitigate this problem, we propose DMNet, a distinguishing and matching-aware unsupervised point cloud completion network. Our work belongs to the group of unsupervised completion methods but goes beyond previous studies. Firstly, we propose a distinguishing-aware feature extractor to learn discriminable semantic information for different instances, simultaneously enhancing the robust invariant representation under noise disturbances. Secondly, we design a hierarchy-aware hyperbolic decoder to recover the complete geometry of point clouds, which not only can capture the implicit hierarchical relationships in data but also has an explicit extended nature. Finally, we develop a matching-aware refiner to eliminate noise points via aligning the topology structure of the input and predicted partial point clouds. Extensive experiments on MVP, Completion3D and KITTI datasets prove the effectiveness of our method, which performs favorably over state-of-the-art methods both quantitatively and qualitatively.

Pyrite (FeS₂) is an attractive photovoltaic material due to its high absorption coefficient and suitable band gap. This work focuses on the effect of external electric field on the electronic band structure and optical properties using density functional theory with Hubbard U correction (DFT+U). Calculations suggest that the application of electric field in x, y and z directions produce similar results both in band structure and optical properties of pyrite. The addition of external electric field has not changed the p-type semiconductivity but band splits significantly and the gap also decreases obviously at high electric field, accompanied with the fracture of the crystal. The variation of dielectric function, absorption coefficient, reflectivity, refractive index, extinction coefficient and conductivity are observed due to the addition of electric field.